QUANTILE FORECASTS OF FINANCIAL RETURNS USING REALIZED GARCH MODELS*

This article applies the realized generalized autoregressive conditional heteroskedasticity (GARCH) model, which incorporates the GARCH model with realized volatility, to quantile forecasts of financial returns, such as Value‐at‐Risk and expected shortfall. Student's t‐ and skewed Student's t‐distributions as well as normal distribution are used for the return distribution. The main results for the S&P 500 stock index are: (i) the realized GARCH model with the skewed Student's t‐distribution performs better than that with the normal and Student's t‐distributions and the exponential GARCH model using the daily returns only; and (ii) using the realized kernel to take account of microstructure noise does not improve the performance.     

ALLOWING FOR JUMP MEASUREMENTS IN VOLATILITY: A HIGH‐FREQUENCY FINANCIAL DATA ANALYSIS OF INDIVIDUAL STOCKS

Following recent advances in the non‐parametric realized volatility approach, we separately measure the discontinuous jump part of the quadratic variation process for individual stocks and incorporate it into heterogeneous autoregressive volatility models. We analyse the distributional properties of the jump measures vis‐à‐vis the corresponding realized volatility ones, and compare them to those of aggregate US market index series. We also demonstrate important gains in the forecasting accuracy of high‐frequency volatility models.     

EMPIRICAL PERFORMANCE OF GARCH MODELS WITH HEAVY‐TAILED INNOVATIONS

We introduce a new type of heavy‐tailed distribution, the normal reciprocal inverse Gaussian distribution (NRIG), to the GARCH and Glosten‐Jagannathan‐Runkle (1993) GARCH models, and compare its empirical performance with two other popular types of heavy‐tailed distribution, the Student's t distribution and the normal inverse Gaussian distribution (NIG), using a variety of asset return series. Our results illustrate that there is no overwhelmingly dominant distribution in fitting the data under the GARCH framework, although the NRIG distribution performs slightly better than the other two types of distribution. For market indexes series, it is important to introduce both GJR‐terms and the NRIG distribution to improve the models’ performance, but it is ambiguous for individual stock prices series. Our results also show the GJR‐GARCH NRIG model has practical advantages in quantitative risk management. Finally, the convergence of numerical solutions in maximum‐likelihood estimation of GARCH and GJR‐GARCH models with the three types of heavy‐tailed distribution is investigated.     

PREDICTING STOCK RETURNS AND VOLATILITY WITH INVESTOR SENTIMENT INDICES: A RECONSIDERATION USING A NONPARAMETRIC CAUSALITY‐IN‐QUANTILES TEST

Evidence of monthly stock returns predictability based on popular investor sentiment indices, namely S^BW and S^PLS as introduced by Baker and Wurgler (2006, 2007) and Huang et al. (2015) respectively are mixed. While, linear predictive models show that only S^PLS can predict excess stock returns, nonparametric models (which accounts for misspecification of the linear frameworks due to nonlinearity and regime changes) finds no evidence of predictability based on either of these two indices for not only stock returns, but also its volatility. However, in this paper, we show that when we use a more general nonparametric causality‐in‐quantiles model of Balcilar et al., (forthcoming), in fact, both S^BW and S^PLS can predict stock returns and its volatility, with S^PLS being a relatively stronger predictor of excess returns during bear and bull regimes, and S^BW being a relatively powerful predictor of volatility of excess stock returns, barring the median of the conditional distribution.     

BANK PERFORMANCE,FINANCIAL STABILITY AND MARKET CONCENTRATION: EVIDENCE FROM COOPERATIVE AND NON‐COOPERATIVE BANKS

Relying upon highly territorially disaggregated data taken at labour market areas, the paper explores the relationship between bank performances and financial stability of the banking system taking into account the role of market concentration. The z‐score is used as financial stability indicator, while the performance of financial intermediaries is measured using a parametric method recently developed (Kumbhakar et al. 2014). The empirical evidence shows a positive relationship between bank performance and financial stability and supports the ‘concentration–stability’ view for non‐cooperative banks only when concentration is measured on the whole sample of banks. Differences in the performance–stability nexus seem to depend more on the type of banks rather than different levels of market concentration. Higher market concentration of cooperative banks affects systemic stability by reducing the z‐scores of non‐cooperative banks, supporting the hypothesis that the presence of non‐profit‐maximizing entities can pull down stability of other financial institutions.     

ROLLING REGRESSION VERSUS TIME‐VARYING COEFFICIENT MODELLING: AN EMPIRICAL INVESTIGATION OF THE OKUN'S LAW IN SOME EURO AREA COUNTRIES

During the last decade, economists have shown that the inverse relationship between economic growth and unemployment rate varies over time. Rolling regression has been the main tool used to quantify such a relationship. This methodology suffers from several well‐known problems which lead to spurious non‐linear patterns in the Okun's coefficient behaviour over time. Here, we take a penalized regression spline approach to estimate the Okun's time‐varying effects. As a result, spurious non‐linearities are suppressed and hence important time‐varying coefficient features revealed. Our empirical results show that the inverse relationship in some Euro area countries is spatially heterogeneous and time‐varying. The findings are complemented by the calculation of the rate of output growth needed for a stable unemployment rate, as proposed by Knotek.     

WHOLESALE PRICES AND COURNOT‐BERTRAND COMPETITION

This note considers the competing vertical structures framework with Cournot‐Bertrand competition downstream. It shows that the equilibrium wholesale price paid by a Cournot (Bertrand)‐type retailer is above (below) marginal costs of a corresponding manufacturer. This result contrasts with the one under pure competition downstream (i.e., Cournot or Bertrand), where the wholesale price is set below (above) marginal costs in case of a Cournot (Bertrand) game at the retail level.     

An effective going concern prediction model for the sustainability of enterprises and capital market development

The purpose of this study is to construct a two-stage effective and innovative going concern prediction model to predict going concern doubt for the sustainability of enterprises and capital market development. Samples of this study are the companies listed on the Taiwan Stock Exchange or the Taipei Exchange, totalling 196 companies and including 49 companies with going concern doubt and 147 normal companies (with no going concern doubt). The data are taken from the Taiwan Economic Journal (TEJ) and the Market Observation Post System during the period from 2001 to 2016 (totalling 16 years). This study adopts a two-stage way to construct the going concern prediction models. In Stage I, the traditional statistical method of stepwise regression (SR) and the data mining technique artificial neural network (ANN) are applied to select the important variables. In Stage II, two decision tree algorithms (data mining techniques): classification and regression tree (CART) and C5.0 are used to establish the prediction models. The results show that the SR + CART model has the highest going concern prediction accuracy, with an overall accuracy of 87.42%.     

China's liberalizing stock market,crude oil,and safe-haven assets: A linkage study based on a novel multivariate wavelet-vine copula approach

China is the world's largest oil importer, and therefore the correlations between stock indices and highly volatile oil prices deserve close examination when investing in China's gradually liberalizing stock market. Another concern for international investors is whether safe-haven assets can reduce portfolio risks for investment in China. The paper makes two main contributions. First, we develop a novel method of examining a multivariate dependence structure by combining wavelet analysis with the vine copula model. Second, we apply the proposed methodology to study the correlations between China's liberalizing stock market, petroleum, and safe-haven assets at different frequencies. We find that the multidimensional dependence of these assets has been altered as a result of the 2008 global financial crisis. Moreover, the vine structures exhibit dependence patterns that vary over time horizons, indicating that the multidimensional dependence is sensitive to time scales.     

Acquisition of Information and Share Prices: An Empirical Investigation of Cognitive Dissonance

Abstract. This paper deals with the determinants of agents' acquisition of information. Our econometric evidence shows that the general index of Italian share‐prices and the series of Italy's financial newspaper sales are cointegrated, and the former series Granger‐causes the latter, thereby giving support to the cognitive dissonance hypothesis: (non‐professional) agents tend to buy the newspaper when share prices are high and not to buy it when share prices are low. Instead, we do not find support for the hypothesis that the agents acquire information in order to trade in the stock market: we find no relationship between quantities exchanged in the market and newspaper sales, nor between stock market volatility and newspaper sales.     

ENDOGENOUS DEBT‐EQUITY RATIO AND BALANCE‐SHEET CHANNEL: IMPLICATIONS FOR GROWTH AND WELFARE

This paper endogenizes the debt‐equity ratio and embodies financial leverage in a cash‐in‐advance model of endogenous growth. Our analysis finds that the debt‐equity ratio is positively related to the balanced‐growth rate, since it serves as a ‘financial accelerator’ to stimulate investment projects. Compared to previous studies, this positive relationship gives rise to an additional balance‐sheet effect, which substantially affects the macroeconomic consequences of monetary and taxation policies. Due to the existence of the balance‐sheet effect, we also find that the Friedman rule is not necessarily optimal.     

SOME OBSERVATIONS ON THE HIGH‐FREQUENCY VERSIONS OF A STANDARD NEW‐KEYNESIAN MODEL

In a small‐scale New‐Keynesian model with a hybrid Phillips curve and IS equation, the paper is concerned with an arbitrary frequency of the agents’ synchronized decision making. It investigates the validity of a fundamental methodological precept according to which no substantive prediction or explanation of a well‐defined macroeconomic period model should depend on the real time length of the period. While this principle is basically satisfied as the period goes to zero, the impulse – response functions of the high‐frequency versions can qualitatively as well as quantitatively be fairly dissimilar from their quarterly counterpart. The result proves to be robust under variations of the degree of price stickiness. The main conclusion is that DSGE modelling may be more sensitive to its choice of the agents’ decision interval.